arXiv AI
Jul 13
The Patchwork Problem in LLM-Generated Code
arXiv:2607. 08981v1 Announce Type: cross Abstract: LLM-generated code often compiles, passes tests, and appears correct, yet breaks once deployed.
Identifying Latent Declarative Representations of Code for Assisting Repository Migration
The paper introduces ADFD‑Migrate, a method that extracts a latent declarative representation of code—an annotated data‑flow diagram (ADFD)—to aid large‑scale repository migration. By using an LLM to infer the source ADFD from repository context and guiding target‑language generation with dependency‑aware chunking, the approach improves porting soundness and completeness. Evaluated on 50 Fortran repositories, the system achieves high behavioral agreement and a superior migration outcome index compared to baseline translation methods.
Related stories
arXiv AI
Aug 19
Benchmarking Automated Security Patch Backporting: How Far Are We?
The paper introduces Porting Benchmark, a curated dataset of 1,234 security patch backporting cases that span cross-version, cross-branch, and cross-repository scenarios, along with a common evaluation framework. Five tools—spanning program analysis, LLM prompting, and LLM agents—are evaluated under aligned settings, revealing that performance varies significantly across tools and that complex patches (Type-IV) see a sharp drop in success rate. The study identifies four root-cause categories for failures and demonstrates that reference-based benchmark scores may not fully capture real-world remediation, as executable validation uncovers additional integration issues.
arXiv AI
Aug 11
A Unified Issue Resolution Benchmark for Requirement Clarification, Planning, and Code Generation for Coding Agents
arXiv:2608. 09072v1 Announce Type: cross Abstract: Large language model-powered coding agents are increasingly used to modify existing code repositories, for example, by adding features or fixing bugs.
Hugging Face Trending Papers
Aug 18
Benchmarking Automated Security Patch Backporting: How Far Are We?
The paper introduces Porting Benchmark, a dataset of 1,234 security patch backporting cases covering cross-version, cross-branch, and cross-repository scenarios, along with a unified evaluation framework. Five tools—spanning program analysis, LLM prompting, and LLM agents—are evaluated under aligned settings, revealing that performance varies significantly across tools and patch complexity, with success rates dropping sharply for structurally complex patches. The study identifies four root-cause categories for failures and demonstrates that reference-based benchmark scores may not fully reflect real-world remediation, as executable validation uncovers additional integration issues.
arXiv AI
Jun 30
SWE-fficiency: Can Language Models Optimize Real-World Repositories on Real Workloads?
arXiv:2511. 06090v3 Announce Type: replace-cross Abstract: Optimizing the performance of large-scale software repositories demands expertise in code reasoning and software engineering (SWE) to reduce runtime while preserving program correctness.
arXiv Machine Learning
Aug 6
ReCodeAgent: A Multi-agent Workflow for Language-Agnostic Translation and Validation of Large-Scale Repositories
arXiv:2604. 07341v2 Announce Type: replace-cross Abstract: Most repository-level code translation and validation techniques have been evaluated on a single source-target programming language (PL) pair, owing to the complex engineering effort required to adapt new PL pairs.
arXiv Machine Learning
Jul 30
MindForge: Teaching Small Language Models Whole-Life-Cycle Software Engineering via Source-Free Program Synthesis
arXiv:2607. 27146v1 Announce Type: cross Abstract: Coding agents have made substantial progress on software engineering tasks that modify existing codebases, including bug fixing and feature implementation.
arXiv AI
5d ago
SWE Refactor Bench: Can Coding Agents Complete a Long-Horizon, Whole-Repository Stack Migration?
The paper introduces SWE Refactor Bench, a benchmark of 20 whole‑repository migrations aimed at testing whether coding agents can autonomously perform long‑horizon stack migrations. It employs a three‑stage evaluation—Migration Audit, Behavioural Tests, and Agentic Verification—to assess both migration completeness and behavioural correctness, revealing that only 5.4 % of runs succeed across all stages. The study shows that agents struggle with migration tasks, especially language rewrites, and highlights the need for more robust coding‑agent capabilities.
arXiv Machine Learning
Jul 22
Spaghetti Architect: A Contamination-Resistant, By-Construction-Labelled, Multi-Language Code Dataset Generator
arXiv:2607. 18642v1 Announce Type: new Abstract: Mined code corpora are abundant but uncontrolled: a snippet's semantics, surface "messiness," and difficulty are whatever the wild contained; there is no known-optimal reference to grade against; and any public sample may already sit in a model's training set.
arXiv AI
Jul 16
SemaDiff: Identifying Semantic-Changing Commits with Generated Code and Tests
arXiv:2607. 13111v1 Announce Type: cross Abstract: Distinguishing semantic-preserving commits from changing ones remains an open challenge in software repository mining.
Hugging Face Trending Papers
Jul 2
Rethinking Complexity Metrics for LLM-Integrated Applications: Beyond Source Code
LLM-integrated applications blend natural language prompts with program code, and much of their runtime behavior originates in the prompt layer rather than in the code itself. Existing complexity metrics, however, operate solely at the code level and therefore overlook this behavioral logic entirely.
arXiv AI
Jul 3
Rethinking Complexity Metrics for LLM-Integrated Applications: Beyond Source Code
arXiv:2607. 01903v1 Announce Type: new Abstract: LLM-integrated applications blend natural language prompts with program code, and much of their runtime behavior originates in the prompt layer rather than in the code itself.